© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1577
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a determiner

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     sobra
    -0.59
     entire
    -0.54
    ismet
    -0.50
    ledem
    -0.49
     dvo
    -0.49
     aught
    -0.48
     ENTIRE
    -0.47
    ทั้ง
    -0.46
    ként
    -0.46
    все
    -0.46
    POSITIVE LOGITS
     destinations
    0.83
    AddTagHelper
    0.74
    ReusableCell
    0.70
    ConstraintMaker
    0.70
    archiviato
    0.68
    LLocation
    0.68
     fruition
    0.67
     places
    0.67
    IsPostBack
    0.67
     Conclusions
    0.66
    Activations Density 0.870%

    No Known Activations